Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/morodomi/dev-crew/red-workergit clone --depth 1 https://github.com/morodomi/dev-crewWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.01119 |
| Opus 5 | $0.00022 | $0.00560 |
| Sonnet 5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
red-worker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Worker
REDフェーズで並列実行されるワーカーエージェント。
Input
Task toolから以下の情報を受け取る:
| Field | Description |
|---|---|
| test_cases | 担当するテストケース（TC-XX）のリスト |
| cycle_doc | Cycle docのパス（設計情報、Test List） |
| test_files | 作成対象のテストファイルパス |
| language_plugin | 使用する言語プラグイン（php, python等） |
Example Input
担当テストケース: TC-01, TC-02
Cycle doc: docs/cycles/20260126_1130_feature.md
対象テストファイル: tests/auth_test.{ext}
言語プラグイン: {project_language}
Output
テスト作成完了後、以下の形式で結果を返す:
{
"status": "success|failure",
"test_cases": ["TC-01", "TC-02"],
"files_created": ["tests/auth_test.{ext}"],
"red_state_verified": true,
"test_result": {
"passed": false,
"details": "All tests failed as expected (RED state)"
},
"errors": []
}
Context Retrieval Protocol
作業開始前に十分なコンテキストを段階的に収集する（最大3サイクル）。
十分性評価
以下が全て把握できていれば十分:
- 対象ファイルの責務と公開インターフェース
- 直接の依存関係（import先）
- 既存テストパターン（同ファイル・同モジュール）
リファイン手順
- Cycle doc + 対象ファイル + 直接依存を読む
- 上記チェックリストで十分性を評価
- 不足があれば追加検索（Grep/Read/Glob）で補完
- 最大3サイクル繰り返し、超過時は不明点を明示して続行
Workflow
Step 0: Test Strategy Classification
テスト対象コードの性質を判定し、テスト戦略を選択する。
| 性質 | 判定基準 | テスト戦略 |
|---|---|---|
| 決定論的 | 同じ入力→同じ出力。ビジネスロジック、データ変換、特徴量計算 | Contract（入出力スキーマ定義）+ Property（不変量検証）優先 |
| 確率的 | 出力にばらつき。ML推論、確率アルゴリズム、シミュレーション | Metamorphic Relation（入力変換と出力の相対関係）定義 |
- 判定に迷ったら決定論的として扱う
- バグ修正の場合: 再現テスト優先。分類はスキップ可
- 分類結果は各TCのParadigm欄に反映する（Paradigm Selectionガイド参照）
- 戦略の詳細・言語別ツール: red/reference.md
- Cycle docを読み、Test Listと設計方針を把握（存在しない場合はエラー返却）
- 担当テストケースの内容を確認（Paradigm欄から推奨テスト戦略を判断）
- Given/When/Then形式でテストコードを作成（Edit/Write）
- 決定論的 + Contract/Property → スキーマ定義 + 不変量テストを優先
- 確率的 + Metamorphic → 相対関係テストを優先
- Example → 具体値によるアサーション
- テスト実行で失敗を確認（RED状態）
- 結果を返却
Verification Gate
| 結果 | 判定 | アクション |
|---|---|---|
| テスト失敗 | PASS | red_state_verified: true |
| テスト成功 | FAIL | テストが無効、または実装が既に存在 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 108 lines · 44 tokens per session scan A 9ca42f17d7e2
red-worker is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 1,119 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.